COVID Cases Analysis

This is a sample notebook ,as modified from https://github.com/dswh/voila-covid-19-dashboard/blob/master/notebooks/covid_19_dashboard.ipynb

the demo is for a dashboard view of viewing COVID 19 cases worldwide

The datasets orginated from John Hopekins and can be downloaded here https://github.com/CSSEGISandData/COVID-19

note:

Case_country.csv is converted from the summary .csv which came from this location: https://github.com/CSSEGISandData/COVID-19/tree/master/csse_covid_19_data/csse_covid_19_daily_reports/csse_covid_19_daily_reports/

# importing libraries

from __future__ import print_function
from IPython.core.display import display, HTML
from ipywidgets import interact, interactive, fixed, interact_manual

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import plotly.express as px
#import folium
import plotly.graph_objects as go
import seaborn as sns
import ipywidgets as widgets

confirmed_df = pd.read_csv ( "./time_series_covid19_confirmed_global.csv")
deaths_df = pd.read_csv ( "./time_series_covid19_deaths_global.csv") 
recovered_df = pd.read_csv ( "./time_series_covid19_recovered_global.csv") 

country_df = pd.read_csv('./cases_country.csv')

confirmed_df.head()

	Province/State	Country/Region	Lat	Long	1/22/20	1/23/20	1/24/20	1/25/20	1/26/20	1/27/20	...	12/28/20	12/29/20	12/30/20	12/31/20	1/1/21	1/2/21	1/3/21	1/4/21	1/5/21	1/6/21
0	NaN	Afghanistan	33.93911	67.709953	0	0	0	0	0	0	...	51280	51350	51405	51526	51526	51526	51526	53011	53105	53105
1	NaN	Albania	41.15330	20.168300	0	0	0	0	0	0	...	56572	57146	57727	58316	58316	58991	59438	59623	60283	61008
2	NaN	Algeria	28.03390	1.659600	0	0	0	0	0	0	...	98631	98988	99311	99610	99897	100159	100408	100645	100873	101120
3	NaN	Andorra	42.50630	1.521800	0	0	0	0	0	0	...	7875	7919	7983	8049	8117	8166	8192	8249	8308	8348
4	NaN	Angola	-11.20270	17.873900	0	0	0	0	0	0	...	17296	17371	17433	17553	17568	17608	17642	17684	17756	17864

5 rows × 355 columns

confirmed_df.shape

(272, 355)

deaths_df.head()

	Province/State	Country/Region	Lat	Long	1/22/20	1/23/20	1/24/20	1/25/20	1/26/20	1/27/20	...	12/28/20	12/29/20	12/30/20	12/31/20	1/1/21	1/2/21	1/3/21	1/4/21	1/5/21	1/6/21
0	NaN	Afghanistan	33.93911	67.709953	0	0	0	0	0	0	...	2174	2179	2181	2191	2191	2191	2191	2237	2244	2244
1	NaN	Albania	41.15330	20.168300	0	0	0	0	0	0	...	1164	1170	1174	1181	1181	1190	1193	1199	1210	1217
2	NaN	Algeria	28.03390	1.659600	0	0	0	0	0	0	...	2737	2745	2751	2756	2762	2769	2772	2777	2782	2786
3	NaN	Andorra	42.50630	1.521800	0	0	0	0	0	0	...	83	84	84	84	84	84	84	84	84	84
4	NaN	Angola	-11.20270	17.873900	0	0	0	0	0	0	...	403	403	405	405	405	407	408	408	410	413

5 rows × 355 columns

deaths_df.head()
deaths_df.shape

(272, 355)

recovered_df.head()
recovered_df.shape

(257, 355)

##CLeaning the data 

confirmed_df.columns = map (str.lower, confirmed_df.columns)
deaths_df.columns = map (str.lower, deaths_df.columns)
recovered_df.columns = map (str.lower, recovered_df.columns)
country_df.columns = map (str.lower, country_df.columns)

confirmed_df.columns

Index(['province/state', 'country/region', 'lat', 'long', '1/22/20', '1/23/20',
       '1/24/20', '1/25/20', '1/26/20', '1/27/20',
       ...
       '12/28/20', '12/29/20', '12/30/20', '12/31/20', '1/1/21', '1/2/21',
       '1/3/21', '1/4/21', '1/5/21', '1/6/21'],
      dtype='object', length=355)

confirmed_df = confirmed_df.rename (columns = {"province/state":"state", "country/region":"country"} )
deaths_df = deaths_df.rename (columns = {"province/State":"state", "country/region":"country"} )
recovered_df = recovered_df.rename (columns = {"province/state":"state", "country/region":"country"} )
country_df = country_df.rename(columns={'country_region': 'country'})

confirmed_df.columns

Index(['state', 'country', 'lat', 'long', '1/22/20', '1/23/20', '1/24/20',
       '1/25/20', '1/26/20', '1/27/20',
       ...
       '12/28/20', '12/29/20', '12/30/20', '12/31/20', '1/1/21', '1/2/21',
       '1/3/21', '1/4/21', '1/5/21', '1/6/21'],
      dtype='object', length=355)

confirmed_total = int(country_df['confirmed'].sum())
deaths_total = int(country_df['deaths'].sum())
recovered_total = int(country_df['recovered'].sum())
active_total = int(country_df['active'].sum())

print ( confirmed_total ) 
print ( deaths_total ) 
print ( recovered_total ) 
print ( active_total ) 

87186540
1883761
48777336
36522525

sorted_country_df = country_df.sort_values('confirmed', ascending= False)

# sorting the values by confirmed descednding order
# country_df.sort_values('confirmed', ascending= False).head(10).style.background_gradient(cmap='copper')
fig = go.FigureWidget( layout=go.Layout() )
def highlight_col(x):
    r = 'background-color: red'
    y = 'background-color: blue'
    g = 'background-color: grey'
    df1 = pd.DataFrame('', index=x.index, columns=x.columns)
    df1.iloc[:, 4] = y
    df1.iloc[:, 5] = r
    df1.iloc[:, 6] = g
    
    return df1

def show_latest_cases(n):
    n = int(n)
    return country_df.sort_values('confirmed', ascending= False).head(n).style.apply(highlight_col, axis=None)

interact(show_latest_cases, n='10')

ipywLayout = widgets.Layout(border='solid 2px green')
ipywLayout.display='none' # uncomment this, run cell again - then the graph/figure disappears
widgets.VBox([fig], layout=ipywLayout)

import plotly.graph_objects as go 

def plot_cases_for_country(country):
    labels = ['confirmed', 'deaths']
    colors = ['blue', 'red']
    mode_size = [6,8] 
    line_size = [4,5]

    df_list = [ confirmed_df, deaths_df ] 
    fig = go.Figure() 

    for i,df in enumerate ( df_list ):
        if country =="World" or country =="world":
            x_data = np.array(list(df.iloc[:, 5:].columns)) #getting all the dates
            y_data = np.sum(np.asarray(df.iloc[:,5:]), axis =0 )
        else:
            x_data = np.array(list(df.iloc[:, 5:].columns))
            y_data = np.sum(np.asarray(df[df["country"]==country].iloc[:,5:]), axis =0 )
        
        fig.add_trace(go.Scatter(x=x_data, y=y_data, mode="lines+markers",
                                 name=labels[i],
                                 line=dict(color=colors[i],width=line_size[i]),
                                 connectgaps=True,
                                  text = "Total "+ str(labels[i]) +":" + str(y_data[-1])
                                 ));
    
    fig.update_layout(
        title="COVID 19 cases of " + country,
        xaxis_title='Date',
        yaxis_title='No. of Confirmed Cases',
        margin=dict(l=20, r=20, t=40, b=20),
        paper_bgcolor="lightgrey",
        width = 800,        
    );
    
    
    fig.update_yaxes(type="linear")
    fig.show()                                    

plot_cases_for_country('US')

plot_cases_for_country('China')

interact(plot_cases_for_country, country='World')

ipywLayout = widgets.Layout(border='solid 2px green')
ipywLayout.display='none' # uncomment this, run cell again - then the graph/figure disappears
widgets.VBox([fig], layout=ipywLayout)

10 worst hit countries - Confirmed cases on a daily basis

columns_drop = ['fips', 'admin2', 'province_state'  ] 
sorted_country_df02 = sorted_country_df.drop(columns=columns_drop)
overall_sorted_country = sorted_country_df02

overall_sorted_country
overall_sorted_country.head(10)

	country	last_update	lat	long_	confirmed	deaths	recovered	active	combined_key	incident_rate	case_fatality_ratio
215	France	2021-01-07 05:22:03	46.227600	2.213700	2701215	66197	174751	2460267.0	France	4138.301919	2.450638
3958	United Kingdom	2021-01-07 05:22:03	52.355500	-1.174300	2450983	67510	0	2383473.0	England, United Kingdom	4378.538048	2.754405
649	Turkey	2021-01-07 05:22:03	38.963700	35.243300	2283931	22070	2164040	97821.0	Turkey	2708.034463	0.966316
268	India	2021-01-07 05:22:03	19.449759	76.108221	1954553	49825	1852759	51969.0	Maharashtra, India	1587.206409	2.549176
6	Argentina	2021-01-07 05:22:03	-38.416100	-63.616700	1676171	43976	1474048	158147.0	Argentina	3708.689420	2.623599
65	Brazil	2021-01-07 05:22:03	-23.550500	-46.633300	1501085	47511	1324431	129143.0	Sao Paulo, Brazil	3268.981028	3.165111
489	Poland	2021-01-07 05:22:03	51.919400	19.145100	1344763	30055	1087744	226964.0	Poland	3553.193212	2.234966
286	Iran	2021-01-07 05:22:03	32.427908	53.688046	1261903	55830	1040521	165552.0	Iran	1502.391516	4.424270
593	South Africa	2021-01-07 05:22:03	-30.559500	22.937500	1149591	31368	929239	188984.0	South Africa	1938.317977	2.728623
263	India	2021-01-07 05:22:03	14.705180	76.166436	924137	12124	902817	9196.0	Karnataka, India	1367.821581	1.311927

px.bar(
    overall_sorted_country.head(10),
    x = "country",
    y = "confirmed",
    title= "Top 10 worst affected countries", # the axis names
    color_discrete_sequence=["pink"], 
    height=500,
    width=800
)
#20200108 - notice that there is 2 indias in the dataset - one came from Maharashtra and another Karnataka

Top 10 Worst Countries having COVID 19 death

top10countries_death = overall_sorted_country.sort_values('deaths', ascending= False)

px.bar(
    top10countries_death.head(10),
    x = "country",
    y = "deaths",
    title= "Top 10 worst affected countries", # the axis names
    color_discrete_sequence=["darkturquoise"], 
    height=500,
    width=800
)
#notice there are 2 regions for brazil as well 

Top 10 Countries in Recovered Cases

top10countries_recovered = overall_sorted_country.sort_values('recovered', ascending= False)

px.bar(
    top10countries_recovered.head(10),
    x = "country",
    y = "recovered",
    title= "Top 10 recovered cases ", # the axis names
    color_discrete_sequence=["green"], 
    height=500,
    width=800
)

#notice there are 2 regions for india as well